SEARCH · Search NASA

Results for “multi-agent”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 55 records · Page 3

All sources NASA NTRS DOE OSTI

DOE OSTI2026

ChemGraph as an agentic framework for computational chemistry workflows

Atomistic simulations are essential in chemistry and materials science but remain challenging to run due to the expert knowledge required for the setup, execution, and validation stages of these calculations. We present ChemGraph, an agentic framework powered by artificial intelligence and state-of-the-art simulation tools to streamline and automate computational chemistry and materials science workflows. ChemGraph leverages graph neural network-based foundation models for accurate yet computationally efficient calculations and large language models (LLMs) for natural language understanding, task planning, and scientific reasoning to provide an intuitive and interactive interface. We evaluate ChemGraph across 13 benchmark tasks and demonstrate that smaller LLMs (GPT-4o-mini, Claude-3.5-haiku, Qwen-2.5-14B) perform well on simple workflows, while more complex tasks benefit from using larger models. Importantly, we show that decomposing complex tasks into smaller subtasks through a multi-agent framework enables GPT-4o to reach perfect accuracy and smaller LLMs to match or exceed single-agent GPT-4o's performance in these benchmarks.

Computational chemistry↗

DOE OSTI2025

A multi-scale cognitive interaction model of instrument operations at the Linac Coherent Light Source

The Linac Coherent Light Source (LCLS) is the world’s first x-ray free electron laser. It is a scientific user facility operated by the SLAC National Accelerator Laboratory, at Stanford, for the U.S. Department of Energy. As beam time at LCLS is extremely valuable and limited, experimental efficiency—getting the most high quality data in the least time—is critical. Our overall project employs cognitive engineering methodologies with the goal of improving experimental efficiency and increasing scientific productivity at LCLS by refining experimental interfaces and workflows, simplifying tasks, reducing errors, and improving operator safety and stress. Here, in this study, we describe a multi-agent, multi-scale computational cognitive interaction model of instrument operations at LCLS. Our model simulates the aspects of human cognition at multiple cognitive and temporal scales, ranging from seconds to hours, and among agents playing multiple roles, including instrument operator, real time data analyst, and experiment manager. The model can roughly predict impacts stemming from proposed changes to operational interfaces and workflows. Example results demonstrate the model’s potential in guiding modifications to improve operational efficiency. We discuss the implications of our effort for cognitive engineering in complex experimental settings and outline future directions for research. The model is open source, and the videos of the supplementary material provide extensive detail.

47 OTHER INSTRUMENTATION↗

DOE OSTI2025

CityLearn v2: energy-flexible, resilient, occupant-centric, and carbon-aware management of grid-interactive communities

As more distributed energy resources become part of the demand-side infrastructure, quantifying their energy flexibility on a community scale is crucial. CityLearn v1 provided an environment for benchmarking control algorithms. However, there is no standardized environment utilizing realistic building-stock datasets for distributed energy resource control benchmarking without co-simulation or third-party frameworks. CityLearn v2 extends CityLearn v1 by providing a stand-alone simulation environment that leverages the End-Use Load Profiles for the U.S. Building Stock dataset to create grid-interactive communities for resilient, multi-agent, and objective control of distributed energy resources with dynamic occupant feedback. While the v1 environment used pre-simulated building thermal loads, the v2 environment uses data-driven thermal dynamics and eliminates the need for co-simulation with building energy performance software. This work details the v2 environment and provides application examples that use reinforcement learning control to manage battery energy storage system, vehicle-to-grid control, and thermal comfort during heat pump power modulation.

Nweye, Kingsley↗

DOE OSTI2026

The ballad of LLM agents: philosophical reasoning for chemistry

Large language models (LLMs) show remarkable potential for scientific reasoning but often produce unreliable or scientifically unactionable outputs when faced with multi-step logic, domain grounding, and interpretability challenges, especially in complex fields like chemistry and materials science. Here, we introduce a framework of philosophical reasoning agents, inspired by canonical thinkers such as Socrates, Descartes, Kant, and Hume, to guide LLM behavior via structured prompt engineering. These agents embody distinct reasoning paradigms (dialectical inquiry, deductive logic, rule-based judgment, and empirical validation) and are evaluated across multiple chemistry subdomains, physical, analytical, general, inorganic, and organic chemistry, using the ChemBench benchmark. Our agentic prompting approach yields substantial accuracy gains on open-ended numerical chemistry questions, with gains of +11.5 percentage points for GPT-4o with Hume, +4.5 percentage points for GPT-5 with Kant, and +21.8 percentage points for GPT-5.1 with Socrates at the strict 1% error threshold, relative to the corresponding base models. Beyond accuracy, we observe benchmark-level model–agent performance patterns, suggesting that different prompting styles interact differently with each base model. These findings demonstrate that embedding philosophy-of-science principles into multi-agent frameworks can improve and produce interpretable, adaptive, and domain-aligned scientific LLMs.

Harb, Hassan [Argonne National Laboratory (ANL), A↗

DOE OSTI2026

Agent-Based Simulation of Price-Demand Dynamics in Multi-Service Charging Station

As the adoption of electric vehicles and hydrogen fuel-cell vehicles grows, understanding how dynamic pricing strategies influence charging and refueling behaviors becomes crucial for optimizing local energy markets. This paper proposes a simulation-based analysis of a hydrogen-electricity integrated charging station that serves both types of vehicles. A multi-agent simulation framework is developed to model the interactions between vehicles and the station, incorporating price- and delay-sensitive behaviors in decision-making. The station can dynamically adjust energy prices, while vehicles optimize their charging or refueling choices based on their utility values. A series of sensitivity analyses are conducted to evaluate how electricity pricing, infrastructure capacity, and waiting behavior impact station performance. Results highlight that moderate electricity prices maximize user participation without sacrificing profit, infrastructure should be right-sized to demand to avoid over- or underutilization, and delay-toleration also affects service outcomes, which may reach the maximum service coverage at the threshold of 45 minutes.

Wang, Xudong [University of Tennessee, Knoxville (↗

DOE OSTI2026

From Rules to Reasoning: A Survey of Large Language Model-Based Approaches to Scientific Hypothesis and Idea Generation

Scientific hypothesis generation represents a fundamental challenge in contemporary research due to exponentially expanding literature volumes and increasing disciplinary specialization. Large language models (LLMs) have emerged as transformative tools for automated scientific discovery, moving beyond traditional rule-based and literature-mining approaches. Four paradigmatic approaches define current LLM-driven hypothesis generation: direct prompting and fine-tuning methods, knowledge-enhanced frameworks integrating retrieval-augmented generation (RAG), multi-agent collaborative systems simulating research teams, and reasoning-focused approaches implementing cognitive architectures. Domain-specific applications demonstrate statistical equivalence to human expert performance in social psychology, experimental validation in biomedical research, and near-expert quality in astronomy. Evaluation methodologies encompass human expert assessment, LLM-as-judge frameworks, and comprehensive benchmarking systems. Technical challenges include hallucination management, knowledge integration limitations, and balancing novelty with feasibility. Future directions emphasize hybrid neural-symbolic architectures and sophisticated human-AI collaboration models for responsible scientific discovery acceleration.

AI-driven discovery↗

DOE OSTI2024

Interdependent Water And Power Infrastructure Model

The approach used is the Multi-Agent System (MAS) paradigms, where systems components are represented as agents, interacting both with each other, and with the environment in which they evolved. Agents behaviors correspond to components in the real Integrated Water-Power System. The model simulate actions and interactions of these (autonomous) agents to analyze their effects on the overall system. Agents in the water system capture components of water collection, treatment, transportation, distribution and use (e.g. pipe, canal, pump, water demands for agriculture, etc.). Agents in the power system capture components of power generation, transportation, distribution and use (electricity demands, sources, etc.).

Toba, Danho Ange Lionel [Idaho National Laboratory↗

DOE OSTI2025

CyRRL (Cyber Resilient Reinforcement Learning for grid voltage control) [SWR-24-115]

This codebase contains a multi-agent, actor-critic reinforcement learning implementation for cyber-resilient grid voltage control. It uses a 123-bus OpenDSS system as the environment, with three-phase power flow translating nodal power injections into solved nodal voltages. The reward function penalizes deviations from nominal voltage as well as reactive power dispatch, while encouraging agents to take actions that result in fast convergence to nominal conditions. The codebase models false data injection attacks and includes functionality for training, testing, hyper-parameter tuning, and visualization.

Murphy, Sinnott [National Renewable Energy Laborat↗

DOE OSTI2026

mada-tools: MCP servers, configurations, skills, and examples for MADA

MADA-tools (Multi-Agent Design Assistant tools) is a library for defining MCP (Model Context Protocol) servers that can be used by AI agents in the MADA project. Each MCP server provides a focused set of tools that enhances an LLM's knowledge and capabilities for a specific domain, for example, how to launch jobs with Flux versus Slurm. The library makes it easy to configure and start multiple MCP servers using configuration files or command line options. Once running, these servers are intended to be consumed by one or more agents in the MADA ecosystem. The system is designed to be extensible so that future projects can contribute their own MCP servers, skills, and toolsets.

Gunnarson, BrianS [Lawrence Livermore National Lab↗

DOE OSTI2026

Wolf

The Workflow Orchestration Language Framework (WOLF) is an agentic framework grounded in natural language with an architecture inspired by reinforcement learning (RL)—designed to orchestrate, scale, and accelerate complex workflows. The concept of WOLF was born out of the very successful ASC Tri-lab Multi-Agent Design Assistant (MADA) project, but extends beyond its domain-specific design agents to provide a more general and extensible architecture. WOLF capitalizes on the lessons learned from MADA and is fully aligned with Sutton’s The Bitter Lesson—that the most enduring progress in AI comes from general-purpose methods that scale with computation, rather than narrow techniques built on domain-specific human knowledge. In this spirit, WOLF enables agents to autonomously learn workflows, capture strategies as reusable playbooks, and build a growing corpus of interpretable, auditable “wisdom artifacts.” These artifacts, expressed in natural language, bridge human and machine understanding while preserving adaptability and scalability as computational power continues to expand.

Boureima, Ismaeal↗

DOE OSTI2024

Generative AI for Power Grid Operations

Generative artificial intelligence (AI) has captured into the mainstream, demonstrating capabilities that once belonged solely to the realm of human cognition. From defeating world champions in complex games to generating human-quality text and images, Generative AI has proven its potential to revolutionize countless industries. The electric power grid is no exception. Generative AI's ability to process vast amounts of data rapidly, assist decision support and identify patterns could significantly enhance power grid operations. For example, Generative AI could improve state estimation where measurements are not available or integrate renewable energy sources more efficiently with probabilistic forecasting. The key contributions of this whitepaper are outlined below: (1) Comprehensive overview of Generative AI's applications in power grid operations: It highlights the opportunities in areas such as forecasting, state estimation, and demonstrating the potential for enhancing efficiency, reliability, and resilience. (2) Expanding Generative AI's impact through synergies with emerging technologies: The paper introduce NREL developed eGridGPT and explores how AI orchestration, multi-agent systems, and Digital Twins can collaborate to optimize grid operations, addressing the complexities of a decarbonized and electrified future. (3) In-depth analysis of challenges in implementing Generative AI: This includes considerations like data availability and quality, model validation, certification, and ethical concerns, ensuring responsible AI deployment. (4) Emphasizing human-AI collaboration: The whitepaper underscores the importance of trustworthy, transparency, and explainability in AI systems to promote seamless interaction between human operators and AI, ultimately improving decision-making. (5) Exploring future research and development: It identifies critical areas for further advancement to fully realize Generative AI's potential in power grid operations. This whitepaper serves as a valuable resource for researchers, practitioners, and policymakers looking to harness Generative AI for a more reliable, stable, and cost-effective power grid.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2024

Self-Aware Local Autonomous and Semi-Cooperative Control for Cross-Layered Resilience (SLAC3R)

The objective of this work is to develop and demonstrate novel, adaptive, lightweight algorithms that enable the decision-making agents in a large cyber-physical network to act both autonomously and in collaborative harmony to enforce assured resilience across spatiotemporal layers, even under unforeseen adversarial scenarios (e.g., high- impact-low-probability events). Towards this end, the proposed solution will serve as minimally invasive add-on layers that bridge the existing (faster, reactive) local myopic controls and (slower, predictive) centralized optimization. Importantly, the proposed algorithms will enable the multi-agent network to autonomously and collaboratively enforce resilient operation under no or limited communication environment typical of severe cyber- physical adversarial events. The expected outcome of this effort is a suite of prototype, open-source, software algorithms for safety-aware local autonomous and semi-cooperative control (SLAC3R), demonstrated on networked microgrids (via RD2C/Thrust-1 OPAL-RT testbed).

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

ReLIC: Full-Scale Realization of Reinforcement Learning for Infrastructure Control

Prior efforts have shown that deep reinforcement learning (DRL) may provide a new method for controlling networked power systems. Though successful, prior approaches have not yet demonstrated their behavior on systems of realistic scale. This effort examined multiple theoretical and technical approaches to allow a DRL model to operate over a system of 2,000 buses or more. We find that allowing the DRL models to run training episodes in parallel provides near limitless efficiency gains, allowing us to train successful agents to behave on our Kuramoto transmission model of up to 4,000 buses. We further show that we can expand our PowerWorld DRL implementation to systems of up to 25 buses but struggle to go beyond this limit due to PowerWorld’s inability to run multiple instances at once. Finally, we examine a multi-agent approach and find that it performs as well if not better than our existing centralized approach.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap

One year ago, the AISLE roadmap argued that autonomous laboratories operated as isolated islands and proposed a grassroots network organized around five critical dimensions. The field has since moved faster than that roadmap anticipated: multi-agent systems have produced experimentally validated hypotheses, self-driving laboratories have grown more interoperable and orchestrated, reasoning-trained and domain foundation models have raised the capability ceiling, and the Genesis Mission has placed autonomous experimentation at the center of U.S. federal science strategy, with industry emerging as a primary actor. Progress has met a sobering counter-current, including a corrected flagship discovery result, benchmarks showing that agents which rival experts on closed-ended questions still complete only a fraction of open-ended research, and fabricated citations surfacing at leading venues. We read this as the defining tension of the field: producing a candidate discovery is no longer the hard part, but verifying it is, and this asymmetry now limits autonomous science more than raw model capability. Accordingly, we update the roadmap around seven dimensions, revisiting the original five and elevating two former cross-cutting concerns, trust, verification, and reproducibility, and safety, security, and governance, to first-class status. We assess the original milestones (M1 through M14) as achieved, partially achieved, reframed, or open, add four new milestones (M15 through M18) for the elevated dimensions, and scope the path forward to a two-year horizon, with the first year concentrating on interfaces, protocol adoption, and the scaffolding of verification, and the second targeting federation, zero-trust coordination, and governance. Throughout, we position the grassroots network as the interoperability fabric that lets national programs, international initiatives, and commercial platforms connect rather than re-silo.

99 GENERAL AND MISCELLANEOUS↗

DOE OSTI2026

Topology-Dependent Performance of Free-Space Photonic Quantum Networks Under Noise

Photonic quantum communication enables secure and high-fidelity information transfer beyond classical limits, with direct relevance to emerging quantum networks operating in free-space environments. While physical-layer models of depolarizing noise, Gamma–Gamma turbulence statistics, entanglement swapping, and decoy-state QKD security bounds are individually well established, prior work typically treats these components in isolation or under fixed network assumptions. In this work, we develop a unified topology-aware analytical framework that simultaneously integrates free-space optical link budgets, turbulence-induced visibility degradation, depolarizing qubit noise, multi-hop entanglement cascade dynamics, teleportation fidelity thresholds, CHSH nonlocality certification, and asymptotic decoy-state secret key rate bounds across star, mesh, and ring graph structures. Rather than introducing new physical channel models, we demonstrate that identical physical links exhibit fundamentally different end-to-end performance once embedded within different network topologies. Mesh architectures minimize visibility cascade through hop-count reduction but incur quadratic hardware scaling. Star topologies minimize link count but concentrate noise and synchronization overhead at the hub. Ring configurations offer linear hardware scaling with multiplicative fidelity degradation. The results establish topology as a first-order design parameter in near-term free-space quantum networks operating without full quantum repeater infrastructures. While motivated by distributed multi-agent architectures, the framework applies broadly to terrestrial, airborne, and satellite-assisted photonic quantum communication systems.

QKD↗

DOE OSTI2024

Towards Agentic AI on Particle Accelerators

As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show two examples, where we demonstrate viability of such architecture.

43 PARTICLE ACCELERATORS↗

DOE OSTI2025

LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers

Liquid cooling is critical for thermal management in high-density data centers with the rising AI workloads. However, machine learning-based controllers are essential to unlock greater energy efficiency and reliability, promoting sustainability. We present LC-Opt, a Sustainable Liquid Cooling (LC) benchmark environment, for reinforcement learning (RL) control strategies in energy-efficient liquid cooling of high-performance computing (HPC) systems. Built on the baseline of a high-fidelity digital twin of Oak Ridge National Lab's Frontier Supercomputer cooling system, LC-Opt provides detailed Modelica-based end-to-end models spanning site-level cooling towers to data center cabinets and server blade groups. RL agents optimize critical thermal controls like liquid supply temperature, flow rate, and granular valve actuation at the IT cabinet level, as well as cooling tower (CT) setpoints through a Gymnasium interface, with dynamic changes in workloads. This environment creates a multi-objective real-time optimization challenge balancing local thermal regulation and global energy efficiency, and also supports additional components like a heat recovery unit (HRU). We benchmark centralized and decentralized multi-agent RL approaches, demonstrate policy distillation into decision and regression trees for interpretable control, and explore LLM-based methods that explain control actions in natural language through an agentic mesh architecture designed to foster user trust and simplify system management. LC-Opt democratizes access to detailed, customizable liquid cooling models, enabling the ML community, operators, and vendors to develop sustainable data center liquid cooling control solutions.

Naug, Avisek [Hewlett Packard Enterprise]↗

DOE OSTI2025

A Novel LDPP-MADDPG Approach for Distributed Power Allocation in mmWave Cellular Networks

This paper considers the problem of distributed beam scheduling and power allocation problem in millimeter- Wave (mmWave) cellular networks, in which multiple Base Stations (BSs) operate as individual operators over a shared spectrum. We propose a novel learning-aided approach that integrates the Lyapunov Drift-Plus-Penalty (LDPP) framework and Multi-agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithms. This offers a powerful approach to learning stable and constraint-aware policies, reaping the joint benefit of both LDPP and MADDPG, in complex multiagent environments. The major challenge for this approach is to integrate these two approaches in a meaningful and effective manner. The key idea to solve this problem is to introduce a novel feature of local observation that incorporates potential negative value of the reward function due to the stochastic constraints introduced by the LDPP framework. Empirical results demonstrate that our proposed scheme outperforms the baseline methods under various conditions.

99 - GENERAL AND MISCELLANEOUS↗